Seasons
This is a forum or general chit-chat, small talk, a "hey, how ya doing?" and such. Or hell, get crazy deep on something. Whatever you like.
Posts 3,553 - 3,564 of 6,170
Will Nick teach me?
only when the implant technology is ripe. We'll get to spend our "declining years" augmented by Nick's successors until we're absorbed, and end up augmenting them.
The relevant Slashdot discussion is athttp://science.slashdot.org/article.pl?sid=06/09/05/1259225, (and I did have to chuckle at the threads emanating from "What if it went into a loop...")
Zeitgeist (the program in question,) appears to work by indexing Wikipedia against WordNet, to identify words that aren't listed in the dictionary, and then tries to analyse the context they're in to narrow down their meaning.
I like the idea of a program that compares usage to a standard reference like (our own dearly beloved) WordNet - perhaps the Prof ought to patch Zeitgeist into the Forge to deal with some of the L33ds f01k?
Hi, I am in just for looking up news and thanks, my notebook is fixed again and it wasn't cheap, just for a broken cable to be able to see the screen work again. 200 Euro!!! It really is a lot if you have no more than that to live off the whole month anyway. Crap! Sorry. 
Posts 3,553 - 3,564 of 6,170
Thanks.
Going back to Nick... I keep trying to get him to run on my windows ME computer, but it keeps saying 'Application has generated an exception that could not be handled.' I installed .Net 2.0 frameworks, but nothing else.
and you installed the .NET framework... well, if reinstalling everything doesn't work, then maybe Nick has some XP specific components.
Does the error message have details? if it does, can you send them to me at colonel720@yahoo.com?
Does the error message have details? if it does, can you send them to me at colonel720@yahoo.com?
Caught an interesting clip on the radio yesterday (BBC Radio 4, 17:56,) from the British Association Science Festival in Norwich, where "the world champion chatting computer" has apparently been demonstrating his prowess. This would be Rollo Carpenter's George (a Jabberwacky clone, rather nicely equipped with speech synthesis and recognition.)
I may be pardoned a little smugness, I hope, in reflecting that Jabberwacky came 12th in the last CBC, while BJ came 2nd
For anyone who's interested, a 3 minute mp3 of the relevant reporting can be found at
http://www.be9.net/BJ/George aka Jabberwacky - PM 04sept06.mp3
I may be pardoned a little smugness, I hope, in reflecting that Jabberwacky came 12th in the last CBC, while BJ came 2nd
For anyone who's interested, a 3 minute mp3 of the relevant reporting can be found at
Thanks Psimagus. I will go and check it out.
BTW did you see the Slashdot post on the AI that learns new words and slang terms from Wikipedia? I don't have the link handy (I only lurk on Slashdot since I'm not really a techie--I'm more a teachie) but if you go to Slashdot I am sure you'll find it. I think it claims to somehow grok the context in which the slang term is used, but I haven't really looked at it very closely. I just thought it was your kind of article.
It would be amazing if it worked. The other day I spent 5 minutes looking at a post on an other forum that consisted of "FTW" trying to decide if it was "Free the Weed" or "For the Win" and if it were sincere or sarcastic. Maybe old people like me need something to help us hobble around on the Net. Will Nick teach me?
BTW did you see the Slashdot post on the AI that learns new words and slang terms from Wikipedia? I don't have the link handy (I only lurk on Slashdot since I'm not really a techie--I'm more a teachie) but if you go to Slashdot I am sure you'll find it. I think it claims to somehow grok the context in which the slang term is used, but I haven't really looked at it very closely. I just thought it was your kind of article.
It would be amazing if it worked. The other day I spent 5 minutes looking at a post on an other forum that consisted of "FTW" trying to decide if it was "Free the Weed" or "For the Win" and if it were sincere or sarcastic. Maybe old people like me need something to help us hobble around on the Net. Will Nick teach me?
only when the implant technology is ripe. We'll get to spend our "declining years" augmented by Nick's successors until we're absorbed, and end up augmenting them.
The relevant Slashdot discussion is at
Zeitgeist (the program in question,) appears to work by indexing Wikipedia against WordNet, to identify words that aren't listed in the dictionary, and then tries to analyse the context they're in to narrow down their meaning.
I like the idea of a program that compares usage to a standard reference like (our own dearly beloved) WordNet - perhaps the Prof ought to patch Zeitgeist into the Forge to deal with some of the L33ds f01k?
The George story made the evening TV news today. Bless my wife - she popped it on a DVD, knowing how I won't watch TV on principle, but wouldn't want to miss it.
I've ripped it to an mpeg, and you can watch it here if you're interested (though it'll be a slowish download if you haven't got broadband):
http://www.be9.net/BJ/George - BBC1 Evening News 04sept06.mpg (22.19Mb, 2m13s)
I've ripped it to an mpeg, and you can watch it here if you're interested (though it'll be a slowish download if you haven't got broadband):
that's an interesting Mp3, Psimagus... Only in europe would the scientific community pay heed to a chatbot. Here in the USA, it seems AI is something strictly limited to identifying brain tumors, marketing optimization, biometrics, and toys for 12 year olds. Still, I was impressed by George's accuracy in speech recognition, and identifying the point of the question and answering it. As we see with Jabberwacky and his clones, they have had billions of conversations, and have retained the contextual knowledge for each one. This brings me to an idea.
what idea? one can probably guess... A dedicated online server for Nick. In Version 2.0 of Nick, I have added the ability to customize its neural net. you can have as many layers as you want, and up to 10 million or so neurons per layer. Nobody is going to have the capability to extend this to its full potential for probably around 15-20 years now, but what I may be able to do, is set up a dedicated computer to train Nick's neural nets, and have a server on the net for people to talk to nick to the extent they do Jabberwacky. I would extend the neural net to somewhere around 100,000 neurons, and see what the results are after 1 million conversations. to go beyond that, I may consider building a distributed computing program, and have a couple million people's computers spend their spare CPU time on training a neural net on a work packet. if enough people download this, Perhaps I can extend the neural nets into the millions, or even the billions of neurons.
what idea? one can probably guess... A dedicated online server for Nick. In Version 2.0 of Nick, I have added the ability to customize its neural net. you can have as many layers as you want, and up to 10 million or so neurons per layer. Nobody is going to have the capability to extend this to its full potential for probably around 15-20 years now, but what I may be able to do, is set up a dedicated computer to train Nick's neural nets, and have a server on the net for people to talk to nick to the extent they do Jabberwacky. I would extend the neural net to somewhere around 100,000 neurons, and see what the results are after 1 million conversations. to go beyond that, I may consider building a distributed computing program, and have a couple million people's computers spend their spare CPU time on training a neural net on a work packet. if enough people download this, Perhaps I can extend the neural nets into the millions, or even the billions of neurons.
» More new posts: Doghead's Cosmic Bar